Zhile Yang

Zhile Yang, Shangqi Guo, Ying Fang et al.

One stream of reinforcement learning research is exploring biologically plausible models and algorithms to simulate biological intelligence and fit neuromorphic hardware. Among them, reward-modulated spike-timing-dependent plasticity (R-STDP) is a recent branch with good potential in energy efficiency. However, current R-STDP methods rely on heuristic designs of local learning rules, thus requiring task-specific expert knowledge. In this paper, we consider a spiking recurrent winner-take-all network, and propose a new R-STDP method, spiking variational policy gradient (SVPG), whose local learning rules are derived from the global policy gradient and thus eliminate the need for heuristic designs. In experiments of MNIST classification and Gym InvertedPendulum, our SVPG achieves good training performance, and also presents better robustness to various kinds of noises than conventional methods.

Wei Yao, Haohan Ma, Hongwen Zhang et al.

Controllable cooperative humanoid manipulation is a fundamental yet challenging problem for embodied intelligence, due to severe data scarcity, complexities in multi-agent coordination, and limited generalization across objects. In this paper, we present SynAgent, a unified framework that enables scalable and physically plausible cooperative manipulation by leveraging Solo-to-Cooperative Agent Synergy to transfer skills from single-agent human-object interaction to multi-agent human-object-human scenarios. To maintain semantic integrity during motion transfer, we introduce an interaction-preserving retargeting method based on an Interact Mesh constructed via Delaunay tetrahedralization, which faithfully maintains spatial relationships among humans and objects. Building upon this refined data, we propose a single-agent pretraining and adaptation paradigm that bootstraps synergistic collaborative behaviors from abundant single-human data through decentralized training and multi-agent PPO. Finally, we develop a trajectory-conditioned generative policy using a conditional VAE, trained via multi-teacher distillation from motion imitation priors to achieve stable and controllable object-level trajectory execution. Extensive experiments demonstrate that SynAgent significantly outperforms existing baselines in both cooperative imitation and trajectory-conditioned control, while generalizing across diverse object geometries. Codes and data will be available after publication. Project Page: http://yw0208.github.io/synagent

Wenjie Sun, Bingzhe Wu, Zhile Yang et al.

Sparse Autoencoders (SAEs) have emerged as a predominant tool in mechanistic interpretability, aiming to identify interpretable monosemantic features. However, how does sparse encoding organize the representations of activation vector from language models? What is the relationship between this organizational paradigm and feature disentanglement as well as reconstruction performance? To address these questions, we propose the SAEMA, which validates the stratified structure of the representation by observing the variability of the rank of the symmetric semipositive definite (SSPD) matrix corresponding to the modal tensor unfolded along the latent tensor with the level of noise added to the residual stream. To systematically investigate how sparse encoding alters representational structures, we define local and global representations, demonstrating that they amplify inter-feature distinctions by merging similar semantic features and introducing additional dimensionality. Furthermore, we intervene the global representation from an optimization perspective, proving a significant causal relationship between their separability and the reconstruction performance. This study explains the principles of sparsity from the perspective of representational geometry and demonstrates the impact of changes in representational structure on reconstruction performance. Particularly emphasizes the necessity of understanding representations and incorporating representational constraints, providing empirical references for developing new interpretable tools and improving SAEs. The code is available at \hyperlink{https://github.com/wenjie1835/SAERepGeo}{https://github.com/wenjie1835/SAERepGeo}.

Feixiang Zhou, Zheheng Jiang, Zhihua Liu et al.

Automated analysis of mouse behaviours is crucial for many applications in neuroscience. However, quantifying mouse behaviours from videos or images remains a challenging problem, where pose estimation plays an important role in describing mouse behaviours. Although deep learning based methods have made promising advances in human pose estimation, they cannot be directly applied to pose estimation of mice due to different physiological natures. Particularly, since mouse body is highly deformable, it is a challenge to accurately locate different keypoints on the mouse body. In this paper, we propose a novel Hourglass network based model, namely Graphical Model based Structured Context Enhancement Network (GM-SCENet) where two effective modules, i.e., Structured Context Mixer (SCM) and Cascaded Multi-Level Supervision (CMLS) are subsequently implemented. SCM can adaptively learn and enhance the proposed structured context information of each mouse part by a novel graphical model that takes into account the motion difference between body parts. Then, the CMLS module is designed to jointly train the proposed SCM and the Hourglass network by generating multi-level information, increasing the robustness of the whole network.Using the multi-level prediction information from SCM and CMLS, we develop an inference method to ensure the accuracy of the localisation results. Finally, we evaluate our proposed approach against several baselines...

Jinzhi Lin, Shengzhong Feng, Zhile Yang et al.

Sparse code multiple access (SCMA) has been one of non-orthogonal multiple access (NOMA) schemes aiming to support high spectral efficiency and ubiquitous access requirements for 5G wireless communication networks. Conventional SCMA approaches are confronting remarkable challenges in designing low complexity high accuracy decoding algorithm and constructing optimum codebooks. Fortunately, the recent spotlighted deep learning technologies are of significant potentials in solving many communication engineering problems. Inspired by this, we explore approaches to improve SCMA performances with the help of deep learning methods. We propose and train a deep neural network (DNN) called DL-SCMA to learn to decode SCMA modulated signals corrupted by additive white Gaussian noise (AWGN). Putting encoding and decoding together, an autoencoder called AE-SCMA is established and trained to generate optimal SCMA codewords and reconstruct original bits. Furthermore, by manipulating the mapping vectors, an autoencoder is able to generalize SCMA, thus a dense code multiple access (DCMA) scheme is proposed. Simulations show that the DNN SCMA decoder significantly outperforms the conventional message passing algorithm (MPA) in terms of bit error rate (BER), symbol error rate (SER) and computational complexity, and AE-SCMA also demonstrates better performances via constructing better SCMA codebooks. The performance of deep learning aided DCMA is superior to the SCMA.